ocrd 3.5.0__py3-none-any.whl → 3.6.0__py3-none-any.whl

ocrd_utils/str.py

@@ -37,13 +37,14 @@ def assert_file_grp_cardinality(grps, n, msg=None):
     if isinstance(grps, str):
         grps = grps.split(',')
     assert len(grps) == n, \
-            "Expected exactly %d output file group%s%s, but '%s' has %d" % (
-                n,
-                '' if n == 1 else 's',
-                ' (%s)' % msg if msg else '',
-                grps,
-                len(grps)
-            )
+        "Expected exactly %d output file group%s%s, but '%s' has %d" % (
+            n,
+            '' if n == 1 else 's',
+            ' (%s)' % msg if msg else '',
+            grps,
+            len(grps)
+        )
+
 
 def concat_padded(base, *args):
     """
@@ -54,18 +55,20 @@ def concat_padded(base, *args):
         if is_string(n):
             ret = "%s_%s" % (ret, n)
         else:
-            ret = "%s_%04i"  % (ret, n)
+            ret = "%s_%04i" % (ret, n)
     return ret
 
+
 def remove_non_path_from_url(url):
     """
     Remove everything from URL after path.
     """
-    url = url.split('?', 1)[0]    # query
-    url = url.split('#', 1)[0]    # fragment identifier
-    url = re.sub(r"/+$", "", url) # trailing slashes
+    url = url.split('?', 1)[0]     # query
+    url = url.split('#', 1)[0]     # fragment identifier
+    url = re.sub(r"/+$", "", url)  # trailing slashes
     return url
 
+
 def make_file_id(ocrd_file, output_file_grp):
     """
     Derive a new file ID for an output file from an existing input file ``ocrd_file``
@@ -101,9 +104,12 @@ def make_file_id(ocrd_file, output_file_grp):
             ret = output_file_grp + '_' + ocrd_file.ID
     return make_xml_id(ret)
 
+
 def make_xml_id(idstr: str) -> str:
     """
-    Turn ``idstr`` into a valid ``xml:id`` literal by replacing ``:`` with ``_``, removing everything non-alphanumeric, ``.`` and ``-`` and prepending `id_` if ``idstr`` starts with a number.
+    Turn ``idstr`` into a valid ``xml:id`` literal by replacing ``:`` with ``_``,
+    removing everything non-alphanumeric, ``.`` and ``-`` and prepending `id_`
+    if ``idstr`` starts with a number.
     """
     ret = idstr
     if not REGEX_FILE_ID.fullmatch(ret):
@@ -113,6 +119,7 @@ def make_xml_id(idstr: str) -> str:
         ret = re.sub(r'[^\w.-]', r'', ret)
     return ret
 
+
 def nth_url_segment(url, n=-1):
     """
     Return the last /-delimited segment of a URL-like string
@@ -127,6 +134,7 @@ def nth_url_segment(url, n=-1):
     except IndexError:
         return ''
 
+
 def get_local_filename(url, start=None):
     """
     Return local filename, optionally relative to ``start``
@@ -150,12 +158,14 @@ def get_local_filename(url, start=None):
         url = url[len(start):]
     return url
 
+
 def is_local_filename(url):
     """
     Whether a url is a local filename.
     """
     # deprecation_warning("Deprecated so we spot inconsistent URL/file handling")
-    return url.startswith('file://') or not('://' in url)
+    return url.startswith('file://') or '://' not in url
+
 
 def is_string(val):
     """
@@ -171,6 +181,7 @@ def parse_json_file_with_comments(val):
     with open(val, 'r', encoding='utf-8') as inputf:
         return parse_json_string_with_comments(inputf.read())
 
+
 def parse_json_string_with_comments(val):
     """
     Parse a string of JSON interspersed with #-prefixed full-line comments
@@ -178,6 +189,7 @@ def parse_json_string_with_comments(val):
     jsonstr = re.sub(r'^\s*#.*$', '', val, flags=re.MULTILINE)
     return json.loads(jsonstr)
 
+
 def parse_json_string_or_file(*values, resolve_preset_file=None):    # pylint: disable=unused-argument
     """
     Parse a string as either the path to a JSON object or a literal JSON object.
@@ -208,6 +220,7 @@ def parse_json_string_or_file(*values, resolve_preset_file=None):    # pylint: d
         ret = {**ret, **value_parsed}
     return ret
 
+
 def safe_filename(url):
     """
     Sanitize input to be safely used as the basename of a local file.
@@ -218,7 +231,8 @@ def safe_filename(url):
     #  print('safe filename: %s -> %s' % (url, ret))
     return ret
 
-def generate_range(start : str, end : str) -> List[str]:
+
+def generate_range(start: str, end: str) -> List[str]:
     """
     Generate a list of strings by incrementing the number part of ``start`` until including ``end``.
     """
@@ -228,7 +242,8 @@ def generate_range(start : str, end : str) -> List[str]:
     except IndexError:
         raise ValueError("Range '%s..%s': could not find numeric part" % (start, end))
     if start[:-len(start_num)] != end[:-len(end_num)]:
-        raise ValueError(f"Range '{start}..{end}' differ in their non-numeric part: '{start[:-len(start_num)]}' != '{end[:-len(end_num)]}'")
+        raise ValueError(f"Range '{start}..{end}' differ in their non-numeric part: "
+                         f"'{start[:-len(start_num)]}' != '{end[:-len(end_num)]}'")
     if start_num == end_num:
         warn("Range '%s..%s': evaluates to the same number")
     for i in range(int(start_num), int(end_num) + 1):
@@ -261,7 +276,8 @@ def partition_list(lst, chunks, chunk_index=None):
         return [ret[chunk_index]]
     return ret
 
-def sparkline(values : List[int]) -> str:
+
+def sparkline(values: List[int]) -> str:
     """
     Render a list of points with block characters
     """

ocrd_validators/json_validator.py

@@ -7,9 +7,11 @@ from jsonschema import Draft201909Validator, ValidationError, validators # pylin
 
 from ocrd_models import ValidationReport
 
+
 class JsonSchemaDeprecationWarning(ValidationError):
     pass
 
+
 # http://python-jsonschema.readthedocs.io/en/latest/faq/
 def extend_with_default(validator_class):
     """
@@ -34,6 +36,7 @@ def extend_with_default(validator_class):
 
 DefaultValidatingDraft20199Validator = extend_with_default(Draft201909Validator)
 
+
 #
 # -------------------------------------------------
 #
@@ -54,7 +57,7 @@ class JsonValidator():
         """
         if isinstance(obj, str):
             obj = json.loads(obj)
-        return JsonValidator(schema)._validate(obj) # pylint: disable=protected-access
+        return JsonValidator(schema)._validate(obj)  # pylint: disable=protected-access
 
     def __init__(self, schema, validator_class=Draft201909Validator):
         """

ocrd_validators/ocrd_tool_validator.py

@@ -6,6 +6,7 @@ See `specs <https://ocr-d.de/en/spec/ocrd_tool>`_.
 from .constants import OCRD_TOOL_SCHEMA
 from .json_validator import DefaultValidatingDraft20199Validator, JsonValidator
 
+
 #
 # -------------------------------------------------
 #
@@ -20,7 +21,7 @@ class OcrdToolValidator(JsonValidator):
         """
         Validate against ``ocrd-tool.json`` schema.
         """
-        return OcrdToolValidator(schema)._validate(obj) # pylint: disable=protected-access
+        return OcrdToolValidator(schema)._validate(obj)  # pylint: disable=protected-access
 
     def __init__(self, schema):
         super().__init__(schema, validator_class=DefaultValidatingDraft20199Validator)

ocrd_validators/ocrd_zip_validator.py

@@ -8,12 +8,13 @@ from shutil import rmtree
 
 from ocrd_utils import getLogger, unzip_file_to_dir
 
-from bagit import Bag, BagValidationError # pylint: disable=no-name-in-module
-from bagit_profile import Profile, ProfileValidationError # pylint: disable=no-name-in-module
+from bagit import Bag, BagValidationError  # pylint: disable=no-name-in-module
+from bagit_profile import Profile, ProfileValidationError  # pylint: disable=no-name-in-module
 
 from .constants import OCRD_BAGIT_PROFILE, OCRD_BAGIT_PROFILE_URL, TMP_BAGIT_PREFIX
 from ocrd_models import ValidationReport
 
+
 #
 # -------------------------------------------------
 #
@@ -58,7 +59,8 @@ class OcrdZipValidator():
             #  for d in e.details:
             #      log = getLogger('ocrd.ocrd_zip_validator')
             #      if isinstance(d, ChecksumMismatch):
-            #          log.error("Validation Error: expected %s to have %s checksum of %s but found %s", d.path, d.algorithm, d.expected, d.found)
+            #          log.error("Validation Error: expected %s to have %s checksum of %s but found %s",
+            #                    d.path, d.algorithm, d.expected, d.found)
             #      else:
             #          log.error("Validation Error: %s", d)
         if failed:
@@ -89,7 +91,6 @@ class OcrdZipValidator():
             bagdir = mkdtemp(prefix=TMP_BAGIT_PREFIX)
             unzip_file_to_dir(self.path_to_zip, bagdir)
 
-
         try:
             bag = Bag(bagdir)
             self._validate_profile(bag)

ocrd_validators/page_validator.py

@@ -119,6 +119,7 @@ class ConsistencyError(Exception):
             f"INCONSISTENCY in {tag} ID '{ID}' of file '{file_id}': "
             f"text results '{actual}' != concatenated '{expected}'")
 
+
 class CoordinateConsistencyError(Exception):
     """
     Exception representing a consistency error in coordinate confinement across levels of a PAGE-XML.
@@ -145,6 +146,7 @@ class CoordinateConsistencyError(Exception):
             f"INCONSISTENCY in {tag} ID '{ID}' of '{file_id}': "
             f"coords '{inner}' not within parent coords '{outer}'")
 
+
 class CoordinateValidityError(Exception):
     """
     Exception representing a validity error of an element's coordinates in PAGE-XML.
@@ -169,12 +171,14 @@ class CoordinateValidityError(Exception):
         super().__init__(
             f"INVALIDITY in {tag} ID '{ID}' of '{file_id}': coords '{points}' - {reason}")
 
+
 def compare_without_whitespace(a, b):
     """
     Compare two strings, ignoring all whitespace.
     """
     return re.sub('\\s+', '', a) == re.sub('\\s+', '', b)
 
+
 def page_get_reading_order(ro, rogroup):
     """
     Add all elements from the given reading order group to the given dictionary.
@@ -197,6 +201,7 @@ def page_get_reading_order(ro, rogroup):
         if not isinstance(elem, (RegionRefType, RegionRefIndexedType)):
             page_get_reading_order(ro, elem)
 
+
 def make_poly(polygon_points):
     """Instantiate a Polygon from a list of point pairs, or return an error string"""
     if len(polygon_points) < 4:
@@ -212,6 +217,7 @@ def make_poly(polygon_points):
         return 'is negative'
     return poly
 
+
 def make_line(line_points):
     """Instantiate a LineString from a list of point pairs, or return an error string"""
     if len(line_points) < 2:
@@ -225,6 +231,7 @@ def make_line(line_points):
         return 'is negative'
     return line
 
+
 @deprecated_alias(strictness='page_textequiv_consistency')
 @deprecated_alias(strategy='page_textequiv_strategy')
 def validate_consistency(node, page_textequiv_consistency, page_textequiv_strategy,
@@ -239,7 +246,7 @@ def validate_consistency(node, page_textequiv_consistency, page_textequiv_strate
     if isinstance(node, (PcGtsType, OcrdPage)):
         # top-level (start recursion)
         node_id = node.get_pcGtsId()
-        node = node.get_Page() # has no .id
+        node = node.get_Page()  # has no .id
         if not readingOrder:
             readingOrder = {}
         ro = node.get_ReadingOrder()
@@ -247,13 +254,13 @@ def validate_consistency(node, page_textequiv_consistency, page_textequiv_strate
             page_get_reading_order(readingOrder, ro.get_OrderedGroup() or ro.get_UnorderedGroup())
         if not joinRelations:
             joinRelations = []
-        relations = node.get_Relations() # get RelationsType
+        relations = node.get_Relations()  # get RelationsType
         if relations:
-            relations = relations.get_Relation() # get list of RelationType
+            relations = relations.get_Relation()  # get list of RelationType
         else:
             relations = []
         for relation in relations:
-            if relation.get_type() == 'join': # ignore 'link' type here
+            if relation.get_type() == 'join':  # ignore 'link' type here
                 joinRelations.append((relation.get_SourceRegionRef().get_regionRef(),
                                       relation.get_TargetRegionRef().get_regionRef()))
     elif isinstance(node, GlyphType):
@@ -277,7 +284,7 @@ def validate_consistency(node, page_textequiv_consistency, page_textequiv_strate
                                                          parent_points, node_poly))
                 log.debug("Invalid coords of %s %s", tag, node_id)
                 consistent = False
-                node_poly = None # don't use in further comparisons
+                node_poly = None  # don't use in further comparisons
         else:
             node_poly = None
     for class_, getterLO, getterRD in _ORDER[1:]:
@@ -314,7 +321,7 @@ def validate_consistency(node, page_textequiv_consistency, page_textequiv_strate
                     # report.add_error(CoordinateValidityError(child_tag, child.id, file_id, child_points))
                     # log.debug("Invalid coords of %s %s", child_tag, child.id)
                     # consistent = False
-                    pass # already reported in recursive call above
+                    pass  # already reported in recursive call above
                 elif not child_poly.within(node_poly.buffer(PARENT_SLACK)):
                     # TODO: automatic repair?
                     report.add_error(CoordinateConsistencyError(child_tag, child.id, file_id,
@@ -344,13 +351,14 @@ def validate_consistency(node, page_textequiv_consistency, page_textequiv_strate
                 if page_textequiv_consistency == 'fix':
                     log.debug("Repaired text of %s %s", tag, node_id)
                     set_text(node, concatenated, page_textequiv_strategy)
-                elif (page_textequiv_consistency == 'strict' # or 'lax' but...
+                elif (page_textequiv_consistency == 'strict'  # or 'lax' but...
                       or not compare_without_whitespace(concatenated, text_results)):
                     log.debug("Inconsistent text of %s %s", tag, node_id)
                     report.add_error(ConsistencyError(tag, node_id, file_id,
                                                       text_results, concatenated))
     return consistent
 
+
 def concatenate(nodes, concatenate_with, page_textequiv_strategy, joins=None):
     """
     Concatenate nodes textually according to https://ocr-d.github.io/page#consistency-of-text-results-on-different-levels
@@ -367,6 +375,7 @@ def concatenate(nodes, concatenate_with, page_textequiv_strategy, joins=None):
         result += get_text(next_node, page_textequiv_strategy)
     return result.strip()
 
+
 def get_text(node, page_textequiv_strategy='first'):
     """
     Get the first or most confident among text results (depending on ``page_textequiv_strategy``).
@@ -399,6 +408,7 @@ def get_text(node, page_textequiv_strategy='first'):
         # fall back to first element
         return textEquivs[0].get_Unicode().strip()
 
+
 def set_text(node, text, page_textequiv_strategy):
     """
     Set the first or most confident among text results (depending on ``page_textequiv_strategy``).
@@ -410,7 +420,7 @@ def set_text(node, text, page_textequiv_strategy):
     text = text.strip()
     textEquivs = node.get_TextEquiv()
     if not textEquivs:
-        node.add_TextEquiv(TextEquivType(Unicode=text)) # or index=0 ?
+        node.add_TextEquiv(TextEquivType(Unicode=text))  # or index=0 ?
     elif page_textequiv_strategy == 'best':
         if len(textEquivs) > 1:
             textEquivsSorted = sorted([x for x in textEquivs if x.conf],
@@ -432,6 +442,7 @@ def set_text(node, text, page_textequiv_strategy):
         # fall back to first element
         textEquivs[0].set_Unicode(text)
 
+
 class PageValidator():
     """
     Validator for `OcrdPage <../ocrd_models/ocrd_models.ocrd_page.html>`.
@@ -477,5 +488,6 @@ class PageValidator():
             raise ValueError("page_textequiv_consistency level %s not implemented" % page_textequiv_consistency)
         report = ValidationReport()
         log.info("Validating input file '%s'", file_id)
-        validate_consistency(page, page_textequiv_consistency, page_textequiv_strategy, check_baseline, check_coords, report, file_id)
+        validate_consistency(page, page_textequiv_consistency, page_textequiv_strategy, check_baseline, check_coords,
+                             report, file_id)
         return report

ocrd_validators/parameter_validator.py

@@ -3,6 +3,7 @@ Validate parameters against ocrd-tool.json.
 """
 from .json_validator import DefaultValidatingDraft20199Validator, JsonValidator
 
+
 #
 # -------------------------------------------------
 #
@@ -12,7 +13,7 @@ class ParameterValidator(JsonValidator):
     JsonValidator validating parametersagains ocrd-tool.json.
     """
 
-    def validate(self, *args, **kwargs): # pylint: disable=arguments-differ
+    def validate(self, *args, **kwargs):  # pylint: disable=arguments-differ
         """
         Validate a parameter dict against a parameter schema from an ocrd-tool.json
 
@@ -39,7 +40,7 @@ class ParameterValidator(JsonValidator):
             if 'required' in p[n]:
                 if p[n]['required']:
                     required.append(n)
-                del(p[n]['required'])
+                del p[n]['required']
         super().__init__({
             "type": "object",
             "required": required,

ocrd_validators/processing_server_config.schema.yml

@@ -68,16 +68,12 @@ properties:
       required:
         - address
         - username
+        - workers
       oneOf:
         - required:
             - password
         - required:
             - path_to_privkey
-      anyOf:
-        - required:
-            - workers
-        - required:
-            - servers
       properties:
         address:
           description: The IP address or domain name of the target machine
@@ -118,34 +114,6 @@ properties:
                   - native
                   - docker
                 default: native
-        servers:
-          description: List of processor servers that will be deployed
-          type: array
-          minItems: 1
-          items:
-            type: object
-            additionalProperties: false
-            required:
-              - name
-              - port
-            properties:
-              name:
-                description: Name of the processor
-                type: string
-                pattern: "^ocrd-.*$"
-                examples:
-                  - ocrd-cis-ocropy-binarize
-                  - ocrd-olena-binarize
-              deploy_type:
-                description: Should the processor server be deployed natively or with Docker
-                type: string
-                enum:
-                  - native
-                  - docker
-                default: native
-              port:
-                description: The port number to be deployed on the host
-                $ref: "#/$defs/port"
 
 $defs:
   address:

ocrd_validators/resource_list_validator.py

@@ -6,6 +6,7 @@ See `specs <https://ocr-d.de/en/spec/cli#processor-resources>`_.
 from .constants import RESOURCE_LIST_SCHEMA
 from .json_validator import DefaultValidatingDraft20199Validator, JsonValidator
 
+
 #
 # -------------------------------------------------
 #
@@ -22,4 +23,5 @@ class OcrdResourceListValidator(JsonValidator):
         """
         if schema is None:
             schema = RESOURCE_LIST_SCHEMA
-        return JsonValidator(schema, validator_class=DefaultValidatingDraft20199Validator)._validate(obj) # pylint: disable=protected-access
+        validator = JsonValidator(schema, validator_class=DefaultValidatingDraft20199Validator)
+        return validator._validate(obj)  # pylint: disable=protected-access

ocrd_validators/workspace_validator.py

@@ -15,6 +15,7 @@ from .page_validator import PageValidator
 from .xsd_page_validator import XsdPageValidator
 from .xsd_mets_validator import XsdMetsValidator
 
+
 #
 # -------------------------------------------------
 #
@@ -57,7 +58,8 @@ class WorkspaceValidator():
                     if page_id:
                         for one_page_id in page_id:
                             if next(workspace.mets.find_files(fileGrp=grp, pageId=one_page_id), None):
-                                report.add_error("Output fileGrp[@USE='%s'] already contains output for page %s" % (grp, one_page_id))
+                                report.add_error("Output fileGrp[@USE='%s'] already contains output for page %s" % (
+                                    grp, one_page_id))
                     else:
                         report.add_error("Output fileGrp[@USE='%s'] already in METS!" % grp)
         return report
@@ -121,10 +123,10 @@ class WorkspaceValidator():
             resolver (:class:`ocrd.Resolver`): Resolver
             mets_url (string): URL of the METS file
             src_dir (string, None): Directory containing mets file
-            skip (list): Validation checks to omit. One or more of 
+            skip (list): Validation checks to omit. One or more of
                 'mets_unique_identifier',
                 'mets_files', 'pixel_density', 'dimension', 'url',
-                'multipage', 'page', 'page_xsd', 'mets_xsd', 
+                'multipage', 'page', 'page_xsd', 'mets_xsd',
                 'mets_fileid_page_pcgtsid'
             download (boolean): Whether to download remote file references
                 temporarily during validation (like a processor would)
@@ -133,7 +135,7 @@ class WorkspaceValidator():
             report (:class:`ValidationReport`) Report on the validity
         """
         validator = WorkspaceValidator(*args, **kwargs)
-        return validator._validate() # pylint: disable=protected-access
+        return validator._validate()  # pylint: disable=protected-access
 
     def _validate(self):
         """
@@ -141,7 +143,7 @@ class WorkspaceValidator():
         """
         try:
             self._resolve_workspace()
-        except Exception as e: # pylint: disable=broad-except
+        except Exception as e:  # pylint: disable=broad-except
             self.log.warning("Failed to instantiate workspace: %s", e)
             self.report.add_error(f"Failed to instantiate workspace: {e}")
             return self.report
@@ -159,7 +161,7 @@ class WorkspaceValidator():
                     self._validate_mets_xsd()
                 if self.page_checks:
                     self._validate_page()
-            except Exception: # pylint: disable=broad-except
+            except Exception:  # pylint: disable=broad-except
                 self.report.add_error(f"Validation aborted with exception: {format_exc()}")
         return self.report
 
@@ -216,9 +218,11 @@ class WorkspaceValidator():
             page = page_from_file(f).get_Page()
             _, _, exif = self.workspace.image_from_page(page, f.pageId)
             if page.imageHeight != exif.height:
-                self.report.add_error(f"PAGE '{f.ID}': @imageHeight != image's actual height ({page.imageHeight} != {exif.height})")
+                self.report.add_error(f"PAGE '{f.ID}': @imageHeight != image's actual height "
+                                      f"({page.imageHeight} != {exif.height})")
             if page.imageWidth != exif.width:
-                self.report.add_error(f"PAGE '{f.ID}': @imageWidth != image's actual width ({page.imageWidth} != {exif.width})")
+                self.report.add_error(f"PAGE '{f.ID}': @imageWidth != image's actual width "
+                                      f"({page.imageWidth} != {exif.width})")
 
     def _validate_multipage(self):
         """
@@ -237,7 +241,8 @@ class WorkspaceValidator():
                 if exif.n_frames > 1:
                     self.report.add_error(f"Image '{f.ID}': More than 1 frame: {exif.n_frames}")
             except FileNotFoundError:
-                self.report.add_error(f"Image '{f.ID}': Could not retrieve (local_filename='{f.local_filename}', url='{f.url}')")
+                self.report.add_error(f"Image '{f.ID}': Could not retrieve "
+                                      f"(local_filename='{f.local_filename}', url='{f.url}')")
                 return
 
     def _validate_pixel_density(self):
@@ -293,10 +298,11 @@ class WorkspaceValidator():
         except StopIteration:
             self.report.add_error("No files")
         for f in self.mets.find_files(**self.find_kwargs):
-            if f._el.get('GROUPID'): # pylint: disable=protected-access
+            if f._el.get('GROUPID'):  # pylint: disable=protected-access
                 self.report.add_notice(f"File '{f.ID}' has GROUPID attribute - document might need an update")
             if not (f.url or f.local_filename):
-                self.report.add_error(f"File '{f.ID}' has neither mets:Flocat[@LOCTYPE='URL']/@xlink:href nor mets:FLocat[@LOCTYPE='OTHER'][@OTHERLOCTYPE='FILE']/xlink:href")
+                self.report.add_error(f"File '{f.ID}' has neither mets:Flocat[@LOCTYPE='URL']/@xlink:href "
+                                      "nor mets:FLocat[@LOCTYPE='OTHER'][@OTHERLOCTYPE='FILE']/xlink:href")
                 continue
             if f.url and 'url' not in self.skip:
                 if re.match(r'^file:/[^/]', f.url):
@@ -322,19 +328,22 @@ class WorkspaceValidator():
                 for err in XsdPageValidator.validate(Path(f.local_filename)).errors:
                     self.report.add_error("%s: %s" % (f.ID, err))
             if 'page' in self.page_checks:
-                page_report = PageValidator.validate(ocrd_file=f,
-                                                     page_textequiv_consistency=self.page_strictness,
-                                                     check_coords=self.page_coordinate_consistency in ['poly', 'both'],
-                                                     check_baseline=self.page_coordinate_consistency in ['baseline', 'both'])
+                page_report = PageValidator.validate(
+                    ocrd_file=f,
+                    page_textequiv_consistency=self.page_strictness,
+                    check_coords=self.page_coordinate_consistency in ['poly', 'both'],
+                    check_baseline=self.page_coordinate_consistency in ['baseline', 'both'])
                 self.report.merge_report(page_report)
             pcgts = page_from_file(f)
             page = pcgts.get_Page()
             if 'dimension' in self.page_checks:
                 img = self.workspace._resolve_image_as_pil(page.imageFilename)
                 if page.imageHeight != img.height:
-                    self.report.add_error(f"PAGE '{f.ID}': @imageHeight != image's actual height ({page.imageHeight} != {img.height})")
+                    self.report.add_error(f"PAGE '{f.ID}': @imageHeight != image's actual height "
+                                          f"({page.imageHeight} != {img.height})")
                 if page.imageWidth != img.width:
-                    self.report.add_error(f"PAGE '{f.ID}': @imageWidth != image's actual width ({page.imageWidth} != {img.width})")
+                    self.report.add_error(f"PAGE '{f.ID}': @imageWidth != image's actual width "
+                                          f"({page.imageWidth} != {img.width})")
             if 'imagefilename' in self.page_checks:
                 imageFilename = page.imageFilename
                 if is_local_filename(imageFilename):
@@ -344,7 +353,8 @@ class WorkspaceValidator():
                 if not self.mets.find_files(**kwargs):
                     self.report.add_error(f"PAGE '{f.ID}': imageFilename '{imageFilename}' not found in METS")
                 if is_local_filename(imageFilename) and not Path(imageFilename).exists():
-                    self.report.add_warning(f"PAGE '{f.ID}': imageFilename '{imageFilename}' points to non-existent local file")
+                    self.report.add_warning(f"PAGE '{f.ID}': imageFilename '{imageFilename}' "
+                                            "points to non-existent local file")
             if 'alternativeimage_filename' in self.page_checks:
                 for altimg in page.get_AllAlternativeImages():
                     if is_local_filename(altimg.filename):
@@ -368,8 +378,8 @@ class WorkspaceValidator():
                                 self.report.add_error(f"PAGE '{f.ID}': {altimg.parent_object_.id} AlternativeImage "
                                                       f"'{altimg.filename}' feature '{feature}' not standardized for PAGE")
             if 'mets_fileid_page_pcgtsid' in self.page_checks and pcgts.pcGtsId != f.ID:
-                self.report.add_warning('pc:PcGts/@pcGtsId differs from mets:file/@ID: "%s" !== "%s"' % (pcgts.pcGtsId or '', f.ID or ''))
-
+                self.report.add_warning('pc:PcGts/@pcGtsId differs from mets:file/@ID: "%s" !== "%s"' % (
+                    pcgts.pcGtsId or '', f.ID or ''))
 
     def _validate_page_xsd(self):
         """

ocrd_validators/xsd_mets_validator.py

@@ -1,6 +1,7 @@
 from .xsd_validator import XsdValidator
 from .constants import XSD_METS_URL
 
+
 class XsdMetsValidator(XsdValidator):
     """
     XML Schema validator.
@@ -14,4 +15,4 @@ class XsdMetsValidator(XsdValidator):
         Args:
             doc (etree.ElementTree|str|bytes):
         """
-        return cls.instance(XSD_METS_URL)._validate(doc) # pylint: disable=protected-access
+        return cls.instance(XSD_METS_URL)._validate(doc)  # pylint: disable=protected-access

ocrd_validators/xsd_page_validator.py

@@ -1,6 +1,7 @@
 from .xsd_validator import XsdValidator
 from .constants import XSD_PAGE_URL
 
+
 class XsdPageValidator(XsdValidator):
     """
     XML Schema validator.
@@ -14,4 +15,4 @@ class XsdPageValidator(XsdValidator):
         Args:
             doc (etree.ElementTree|str|bytes):
         """
-        return cls.instance(XSD_PAGE_URL)._validate(doc) # pylint: disable=protected-access
+        return cls.instance(XSD_PAGE_URL)._validate(doc)  # pylint: disable=protected-access